Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seo, Sangwoo, Kim, Sungwon, Jung, Jihyeong, Lee, Yoonho, Park, Chanyoung
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929391859138560
author Seo, Sangwoo
Kim, Sungwon
Jung, Jihyeong
Lee, Yoonho
Park, Chanyoung
author_facet Seo, Sangwoo
Kim, Sungwon
Jung, Jihyeong
Lee, Yoonho
Park, Chanyoung
contents Temporal Graph Neural Networks (TGNN) have the ability to capture both the graph topology and dynamic dependencies of interactions within a graph over time. There has been a growing need to explain the predictions of TGNN models due to the difficulty in identifying how past events influence their predictions. Since the explanation model for a static graph cannot be readily applied to temporal graphs due to its inability to capture temporal dependencies, recent studies proposed explanation models for temporal graphs. However, existing explanation models for temporal graphs rely on post-hoc explanations, requiring separate models for prediction and explanation, which is limited in two aspects: efficiency and accuracy of explanation. In this work, we propose a novel built-in explanation framework for temporal graphs, called Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck (TGIB). TGIB provides explanations for event occurrences by introducing stochasticity in each temporal event based on the Information Bottleneck theory. Experimental results demonstrate the superiority of TGIB in terms of both the link prediction performance and explainability compared to state-of-the-art methods. This is the first work that simultaneously performs prediction and explanation for temporal graphs in an end-to-end manner.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13214
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck
Seo, Sangwoo
Kim, Sungwon
Jung, Jihyeong
Lee, Yoonho
Park, Chanyoung
Machine Learning
Temporal Graph Neural Networks (TGNN) have the ability to capture both the graph topology and dynamic dependencies of interactions within a graph over time. There has been a growing need to explain the predictions of TGNN models due to the difficulty in identifying how past events influence their predictions. Since the explanation model for a static graph cannot be readily applied to temporal graphs due to its inability to capture temporal dependencies, recent studies proposed explanation models for temporal graphs. However, existing explanation models for temporal graphs rely on post-hoc explanations, requiring separate models for prediction and explanation, which is limited in two aspects: efficiency and accuracy of explanation. In this work, we propose a novel built-in explanation framework for temporal graphs, called Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck (TGIB). TGIB provides explanations for event occurrences by introducing stochasticity in each temporal event based on the Information Bottleneck theory. Experimental results demonstrate the superiority of TGIB in terms of both the link prediction performance and explainability compared to state-of-the-art methods. This is the first work that simultaneously performs prediction and explanation for temporal graphs in an end-to-end manner.
title Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck
topic Machine Learning
url https://arxiv.org/abs/2406.13214